基于粒子群优化小波神经网络的行程时间预测

PDF(1833 KB)

交通运输研究 ›› 2020, Vol. 6 ›› Issue (2) : 40-47.

于泉，孙瑶

作者信息 +

Travel Time Prediction Based on Particle Swarm Optimization Wavelet Neural Network

Yu Quan, Sun Yao

Author information +

文章历史 +

摘要

为使道路使用者在出发前获得具有高实时性和可靠性的行程时间预测信息，提高出行效率，需提升高速公路行程时间的预测精度。鉴于此，将生物学中粒子群优化算法（Particle Swarm Optimization Algorithm, PSO）引入小波神经网络（Wavelet Neural Network, WNN）中，构建基于粒子群优化小波神经网络（Particle Swarm Optimization Wavelet Neural Network, PSO-WNN）的高速公路行程时间预测模型。首先将高速公路原始收费数据规整化，截取其中有效字段，获取研究路段一个月的行程时间数据并对其进行数据处理。然后分别基于PSO-WNN模型和WNN模型，利用Matlab进行实验。实验结果显示，PSO-WNN模型预测结果的平均绝对误差、平均相对误差和均方误差较WNN模型分别降低了83.36%, 82.20%和98.15%。PSO-WNN行程时间预测模型不仅预测精度高，而且能较准确地预测出行程时间的走向及波动情况，在收敛速度方面也呈现出一定的优势，具有较好的适应能力。

Abstract

In order to make road users obtain highly real-time and reliable travel time prediction information before departure and improve the travel efficiency, the prediction accuracy of the expressway travel time should be improved. Given this, Particle Swarm Optimization(PSO) Algorithm in biology was introduced to Wavelet Neural Network(WNN), and a highway travel time prediction model based on Particle Swarm Optimization Wavelet Neural Network(PSO-WNN) was constructed. First, the original toll data of expressway was normalized, and the valid fields were intercepted. The travel time data covering the research section for one month was acquired and processed. Then, experiments based on PSO-WNN model and WNN model were carried out respectively by using Matlab. The simulation results showed that the mean absolute error, mean relative error and mean square error of the prediction results of PSO-WNN decreased by 83.36%, 82.20% and 98.15% respectively, compared with these of WNN. PSO-WNN travel time prediction model not only has high prediction accuracy, but also can accurately predict the travel time trend and fluctuation. It also has certain advantages in convergence speed and adaptability.

导出引用

于泉, 孙瑶. 基于粒子群优化小波神经网络的行程时间预测[J]. 交通运输研究. 2020, 6(2): 40-47

Yu Quan, Sun Yao. Travel Time Prediction Based on Particle Swarm Optimization Wavelet Neural Network[J]. Transport Research. 2020, 6(2): 40-47

参考文献

[1]Xu L Q, Du X D, Wang B G. Short-Term Traffic Flow Prediction Model of Wavelet Neural Network Based on Mind Evolutionary Algorithm[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2018, 32(12): 1850041.
[2]Gao G R, Liu Y P. Traffic Flow Forecasting Based on PCA and Wavelet Neural Network[C]// 2010 International Conference of Information Science and Management Engineering. Xi′an: IEEE, 2010: 158-161.
[3]Tian W Q, Zhao P, Qiao K. Railway Freight Volume Forecast Based on GRA-WD-WNN[C]// 2019 4th International Conference on Intelligent Transportation Engineering (ICITE). Singapore: IEEE, 2019: 84-88.
[4]Qiu J, Du Q F, Wang W, et al. Short-Term Performance Metrics Forecasting for Virtual Machine to Support Anomaly Detection Using Hybrid ARIMA-WNN Model[C]// 2019 IEEE 43rd Annual Computer Software and Applications Conference (COMPSAC). Milwaukee: IEEE, 2019: 330-335.
[5]李会超，李鸿，张博. 基于遗传算法优化小波神经网络的短时交通流量预测[J]. 计算机应用与软件，2018，35（7）：148-152.
[6]刘亚东. 基于混沌理论和小波神经网络的拥挤交通流短时预测[D]. 重庆：重庆邮电大学，2018.
[7]蒋婷婷. 基于鸡群算法的小波神经网络短时交通流预测研究[D]. 成都：西南交通大学，2018.
[8]郑俊褒，饶珊珊. 改进蛙跳算法的小波神经网络短时交通流预测[J/OL]. 软件导刊. [2019-11-26].
[9]刘丽. 高速公路收费系统设计[J]. 电子技术与软件工程，2019，8（1）：103.
[10]陈娇娜. 大数据驱动下的高速公路交通运行状态评价与分析[D]. 西安：长安大学，2016.
[11]张洁. 基于浮动车轨迹的数据挖掘及其在现代物流中的应用分析[D]. 西安：西安理工大学，2017.
[12]周建伟. 高速公路路径行程时间可靠性研究[D]. 广州：华南理工大学，2015.
[13]毛燕. 四分位法和迭代法对数据分散的能力验证检测数据统计分析结果的比较[J]. 冶金分析，2016， 36（5）：76-81.
[14]Dejong K A. An Analysis of the Behavior of a Class of Genetic Adaptive Systems[D]. Michigan: University of Michigan, 1975．
[15]陈建功，陈晓东. 基于小波函数的锚杆拉拔全过程分析[J]. 岩土力学，2019（12）：1-8.
[16]Sugiki H, Sugiki K. The Scalographic Pattern of Morlet Continuous Wavelet Transform can Differentiate Bileaflet Valve Function[J]. Journal of Artificial Organs, 2018, 21(3): 308-316.
[17]孙伟，常虹，赵巧芝. 基于量子和声优化的改进DMSFE组合模型及在中长期电量预测中的应用[J]. 电力系统保护与控制，2014，42（21）：66-73.
[18]袁媛，邵春福，林秋映，等. 基于RBF神经网络的交通流数据修复研究[J]. 交通运输研究，2016，2（5）：46-52.
[19]张炎亮，陈鑫，李亚东. 小波神经网络模型的改进方法[J]. 计算机应用，2013，33（11）：3107-3110，3143.
[20]张雯雰，王刚，朱朝晖，等. 粒子群优化算法种群规模的选择[J]. 计算机系统应用，2010，19（5）：125-128.